Find answers from the community

a
amamr
Offline, last seen 3 months ago
Joined September 25, 2024
HEY guys,i get this error trying the llama agents example of two agents:
Plain Text
 
ImportError                               Traceback (most recent call last)
Cell In[1], line 1
----> 1 from llama_agents import (
      2     AgentService,
      3     AgentOrchestrator,
      4     ControlPlaneServer,
      5     SimpleMessageQueue,
      6 )
      8 from llama_index.core.agent import ReActAgent
      9 from llama_index.core.tools import FunctionTool

File c:\Users\admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_agents\__init__.py:2
      1 from llama_agents.client import AsyncLlamaAgentsClient, LlamaAgentsClient
----> 2 from llama_agents.control_plane import ControlPlaneServer
      3 from llama_agents.launchers import LocalLauncher, ServerLauncher
      4 from llama_agents.message_consumers import CallableMessageConsumer

File c:\Users\admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_agents\control_plane\__init__.py:2
      1 from llama_agents.control_plane.base import BaseControlPlane
----> 2 from llama_agents.control_plane.server import ControlPlaneServer
      4 __all__ = ["BaseControlPlane", "ControlPlaneServer"]

File c:\Users\admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_agents\control_plane\server.py:23
     21 from llama_agents.message_queues.base import BaseMessageQueue, PublishCallback
...
----> 6 from llama_index.core.query_pipeline.query import RunState
      7 from llama_index.core.tools import BaseTool
      9 from llama_agents.messages.base import QueueMessage

ImportError: cannot import name 'RunState' from 'llama_index.core.query_pipeline.query' (c:\Users\admin\AppData\Local\Programs\Python\Python312\Lib\site-packages\llama_index\core\query_pipeline\query.py)
4 comments
a
W
hello guys , a technical question , can i create a single vector store(it's so i can create a single query engine that has all the documents but each documents has a different data) using mutiple documents that have different metadata ?
"for file_name,category,date in data: docs = SimpleDirectoryReader( input_files=[f"./documents/{file_name}"] ).load_data() docs.metadata = {"filename": "<doc_file_name>","date":date,"category":category}"
is it possible to make a single vector off these documents ? pass all these docs as an array , ill appreciate the help guys.
16 comments
a
W
hello guys, i have a problem acccessing agents prompts and changing them
26 comments
a
L
out of nowhere im getting this new error :
TypeError: ForwardRef._evaluate() missing 1 required keyword-only argument: 'recursive_guard'
5 comments
L
a